orca

Orca runs a fleet of coding agents side by side so you can pick the winner. Point it at a task and it spins up several agents (Claude Code, Codex, OpenCode, whatever you already use), each working in its own isolated git worktree, then you compare the diffs and merge the one that got it right. It is a desktop app for macOS, Windows, and Linux, MIT licensed, and free.

There is no server to run here. You download the app, point it at CLI agents you already have installed, and it handles the worktree juggling, terminal splits, and a built-in browser for checking your work. The one real cost is your own agent subscriptions: Orca does not sell you tokens, it drives the tools you already pay for. There is a mobile companion app too if you want to kick off runs from your phone.

For a solo developer who runs one agent at a time, this is a workflow upgrade the day you install it, and it costs nothing. Small teams get the same benefit per person. There is no team-server or seat-licensing story because there is nothing hosted; everyone runs their own copy against their own subscriptions.

The catch is that parallel agents multiply your token spend fast. Running five agents on the same task means paying for five attempts to keep one. That math is fine when the task is hard and getting it right matters, and wasteful when you are burning frontier-model calls on something a single agent would have nailed. Orca gives you the fleet; deciding when the fleet is worth it is on you.